© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 27754
    Prev
    Next
    INDEX
    Explanations

    array index [0]

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron fires on standalone numeric literals (especially small integers used as indices or constants) in code.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     again
    -1.02
     they
    -1.02
     törvény
    -1.02
     joão
    -1.02
     only
    -0.99
     szabály
    -0.99
    他們
    -0.98
     actually
    -0.98
    他们
    -0.98
     include
    -0.95
    POSITIVE LOGITS
    大多
    0.90
     ребенку
    0.87
    گروه
    0.87
     initComponents
    0.87
     '/';
    0.87
    较为
    0.86
     lider
    0.86
    ار
    0.86
    Eigenschaften
    0.84
     mimo
    0.82
    Activations Density 0.005%

    No Known Activations